The AI arena is free today

Open Superagent

Magistral Medium vs MiniMax M1 40K

MiniMax M1 40K leads the LLM Stats Score 20.8 to 13.3.

Mistral AI · MiniMax · Updated for 2026

Which is better?

MiniMax M1 40K leads the overall LLM Stats Score 20.8 to 13.3, ranking #184 overall.

In the 5 individual benchmarks reported for both models, MiniMax M1 40K wins 3; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Magistral Medium

  • you are already invested in the Mistral AI ecosystem

Choose MiniMax M1 40K

  • overall performance matters — it scores 20.8 and ranks #184 on LLM Stats
  • you value its reported benchmark strengths — it wins 3 of 5 exact shared results
  • you want the most recent training data — it shipped Jun 2025

At a glance

The differences that matter most.

Core performance indexes
13.3
#236
20.8
#184
13.5
#227
21.0
#175
3.7
#209
8.4
#175
Cost, coverage & limits
Benchmark wins
2 of 5
3 of 5
Input price
— / M
— / M
Output price
— / M
— / M
Context window

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Magistral Medium
MiniMax M1 40K
11.7#235
18.2#176
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

6 reported for Magistral Medium · 16 for MiniMax M1 40K

5 shared

Magistral Medium outperforms in 2 benchmarks (GPQA, Humanity's Last Exam), while MiniMax M1 40K is better at 3 benchmarks (AIME 2024, AIME 2025, LiveCodeBench).

MiniMax M1 40K has a slight edge in benchmark performance.

Tue Sep 08 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

432.0B diff

MiniMax M1 40K has 432.0B more parameters than Magistral Medium, making it 1800.0% larger.

Mistral AI
Magistral Medium
24.0Bparameters
MiniMax
MiniMax M1 40K
456.0Bparameters
24.0B
Magistral Medium
456.0B
MiniMax M1 40K

Input capabilities

Documented input modalities across available providers

Magistral Medium supports multimodal inputs, whereas MiniMax M1 40K does not.

Magistral Medium can handle both text and other forms of data like images, making it suitable for multimodal applications.

Magistral Medium

Text
Images
Audio
Video

MiniMax M1 40K

Text
Images
Audio
Video

License

Usage and distribution terms

Magistral Medium is licensed under Apache 2.0, while MiniMax M1 40K uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

Magistral Medium

Apache 2.0

Open weights

MiniMax M1 40K

MIT

Open weights

Release Timeline

When each model was launched

Magistral Medium was released on 2025-06-10, while MiniMax M1 40K was released on 2025-06-16.

MiniMax M1 40K is 0 month newer than Magistral Medium.

Magistral Medium

Jun 10, 2025

1.2 years ago

MiniMax M1 40K

Jun 16, 2025

1.2 years ago

6d newer

Knowledge Cutoff

When training data ends

Magistral Medium has a documented knowledge cutoff of 2025-06-01, while MiniMax M1 40K's cutoff date is not specified.

We can confirm Magistral Medium's training data extends to 2025-06-01, but cannot make a direct comparison without MiniMax M1 40K's cutoff date.

Magistral Medium

Jun 2025

MiniMax M1 40K

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Magistral Medium and MiniMax M1 40K side-by-side, then vote on the output you prefer.

Magistral Medium
✓ Preferred
MiniMax M1 40K
Open in Playground

FAQ

Common questions about Magistral Medium vs MiniMax M1 40K.

Which is better, Magistral Medium or MiniMax M1 40K?

MiniMax M1 40K leads the LLM Stats Score 20.8 to 13.3. Magistral Medium is made by Mistral AI and MiniMax M1 40K is made by MiniMax. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Magistral Medium compare to MiniMax M1 40K in benchmarks?

Magistral Medium scores AIME 2024: 73.6%, GPQA: 70.8%, AIME 2025: 64.9%, LiveCodeBench: 50.3%, Aider-Polyglot: 47.1%. MiniMax M1 40K scores MATH-500: 96.0%, AIME 2024: 83.3%, MMLU-Pro: 80.6%, ZebraLogic: 80.1%, OpenAI-MRCR: 2 needle 128k: 76.1%.

What are the main differences between Magistral Medium and MiniMax M1 40K?

Key differences include LLM Stats Score (13.3 vs 20.8), multimodal support (yes vs no), licensing (Apache 2.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Magistral Medium and MiniMax M1 40K?

Magistral Medium is developed by Mistral AI and MiniMax M1 40K is developed by MiniMax.